{
  "best_metric": 0.32603439688682556,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.03218474040995313,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006436948081990626,
      "grad_norm": 0.4801550507545471,
      "learning_rate": 5e-05,
      "loss": 0.3484,
      "step": 1
    },
    {
      "epoch": 0.0006436948081990626,
      "eval_loss": 1.1717808246612549,
      "eval_runtime": 633.1994,
      "eval_samples_per_second": 33.058,
      "eval_steps_per_second": 4.133,
      "step": 1
    },
    {
      "epoch": 0.0012873896163981251,
      "grad_norm": 0.8900830149650574,
      "learning_rate": 0.0001,
      "loss": 0.5738,
      "step": 2
    },
    {
      "epoch": 0.001931084424597188,
      "grad_norm": 1.00126051902771,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.6358,
      "step": 3
    },
    {
      "epoch": 0.0025747792327962503,
      "grad_norm": 0.9445592164993286,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.4532,
      "step": 4
    },
    {
      "epoch": 0.0032184740409953133,
      "grad_norm": 0.5817092061042786,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.3681,
      "step": 5
    },
    {
      "epoch": 0.003862168849194376,
      "grad_norm": 0.4831136465072632,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.3118,
      "step": 6
    },
    {
      "epoch": 0.004505863657393438,
      "grad_norm": 0.4428505599498749,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.3961,
      "step": 7
    },
    {
      "epoch": 0.005149558465592501,
      "grad_norm": 0.35448750853538513,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.3259,
      "step": 8
    },
    {
      "epoch": 0.005793253273791563,
      "grad_norm": 0.37589535117149353,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.3458,
      "step": 9
    },
    {
      "epoch": 0.006436948081990627,
      "grad_norm": 0.31492888927459717,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2624,
      "step": 10
    },
    {
      "epoch": 0.007080642890189689,
      "grad_norm": 0.48516955971717834,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.3889,
      "step": 11
    },
    {
      "epoch": 0.007724337698388752,
      "grad_norm": 0.6700056195259094,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.4754,
      "step": 12
    },
    {
      "epoch": 0.008368032506587814,
      "grad_norm": 0.2627522349357605,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.2975,
      "step": 13
    },
    {
      "epoch": 0.009011727314786876,
      "grad_norm": 0.19823676347732544,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.2335,
      "step": 14
    },
    {
      "epoch": 0.00965542212298594,
      "grad_norm": 0.2131778597831726,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.2454,
      "step": 15
    },
    {
      "epoch": 0.010299116931185001,
      "grad_norm": 0.2508775591850281,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.2936,
      "step": 16
    },
    {
      "epoch": 0.010942811739384065,
      "grad_norm": 0.2384842187166214,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.2254,
      "step": 17
    },
    {
      "epoch": 0.011586506547583126,
      "grad_norm": 0.27745360136032104,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3009,
      "step": 18
    },
    {
      "epoch": 0.01223020135578219,
      "grad_norm": 0.31106260418891907,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.2943,
      "step": 19
    },
    {
      "epoch": 0.012873896163981253,
      "grad_norm": 0.3090256154537201,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.3145,
      "step": 20
    },
    {
      "epoch": 0.013517590972180315,
      "grad_norm": 0.2793347239494324,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.3245,
      "step": 21
    },
    {
      "epoch": 0.014161285780379378,
      "grad_norm": 0.30441588163375854,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.335,
      "step": 22
    },
    {
      "epoch": 0.01480498058857844,
      "grad_norm": 0.3480492830276489,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.312,
      "step": 23
    },
    {
      "epoch": 0.015448675396777503,
      "grad_norm": 0.3419431447982788,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.3385,
      "step": 24
    },
    {
      "epoch": 0.016092370204976565,
      "grad_norm": 0.49442407488822937,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.4694,
      "step": 25
    },
    {
      "epoch": 0.016092370204976565,
      "eval_loss": 0.33662736415863037,
      "eval_runtime": 633.5543,
      "eval_samples_per_second": 33.039,
      "eval_steps_per_second": 4.131,
      "step": 25
    },
    {
      "epoch": 0.01673606501317563,
      "grad_norm": 0.1330234706401825,
      "learning_rate": 5e-05,
      "loss": 0.2149,
      "step": 26
    },
    {
      "epoch": 0.017379759821374692,
      "grad_norm": 0.18368133902549744,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.2541,
      "step": 27
    },
    {
      "epoch": 0.018023454629573752,
      "grad_norm": 0.1871601641178131,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.2284,
      "step": 28
    },
    {
      "epoch": 0.018667149437772815,
      "grad_norm": 0.25672218203544617,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.2669,
      "step": 29
    },
    {
      "epoch": 0.01931084424597188,
      "grad_norm": 0.22058886289596558,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.2587,
      "step": 30
    },
    {
      "epoch": 0.019954539054170942,
      "grad_norm": 0.21751423180103302,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.2583,
      "step": 31
    },
    {
      "epoch": 0.020598233862370002,
      "grad_norm": 0.24312442541122437,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.2602,
      "step": 32
    },
    {
      "epoch": 0.021241928670569066,
      "grad_norm": 0.28104859590530396,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.2916,
      "step": 33
    },
    {
      "epoch": 0.02188562347876813,
      "grad_norm": 0.26052653789520264,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.287,
      "step": 34
    },
    {
      "epoch": 0.022529318286967193,
      "grad_norm": 0.28748980164527893,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.2935,
      "step": 35
    },
    {
      "epoch": 0.023173013095166253,
      "grad_norm": 0.33002161979675293,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.333,
      "step": 36
    },
    {
      "epoch": 0.023816707903365316,
      "grad_norm": 0.4679362177848816,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.3874,
      "step": 37
    },
    {
      "epoch": 0.02446040271156438,
      "grad_norm": 0.16794776916503906,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.2197,
      "step": 38
    },
    {
      "epoch": 0.025104097519763443,
      "grad_norm": 0.17064571380615234,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.2548,
      "step": 39
    },
    {
      "epoch": 0.025747792327962506,
      "grad_norm": 0.15181192755699158,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.2173,
      "step": 40
    },
    {
      "epoch": 0.026391487136161566,
      "grad_norm": 0.1739838421344757,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.2321,
      "step": 41
    },
    {
      "epoch": 0.02703518194436063,
      "grad_norm": 0.1635858714580536,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2087,
      "step": 42
    },
    {
      "epoch": 0.027678876752559693,
      "grad_norm": 0.20415830612182617,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.2588,
      "step": 43
    },
    {
      "epoch": 0.028322571560758757,
      "grad_norm": 0.21352346241474152,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.2543,
      "step": 44
    },
    {
      "epoch": 0.028966266368957817,
      "grad_norm": 0.2400074601173401,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.2767,
      "step": 45
    },
    {
      "epoch": 0.02960996117715688,
      "grad_norm": 0.22325584292411804,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.2616,
      "step": 46
    },
    {
      "epoch": 0.030253655985355943,
      "grad_norm": 0.22152790427207947,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.2494,
      "step": 47
    },
    {
      "epoch": 0.030897350793555007,
      "grad_norm": 0.2652023732662201,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.2918,
      "step": 48
    },
    {
      "epoch": 0.03154104560175407,
      "grad_norm": 0.41260552406311035,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.3789,
      "step": 49
    },
    {
      "epoch": 0.03218474040995313,
      "grad_norm": 0.4374171793460846,
      "learning_rate": 0.0,
      "loss": 0.4499,
      "step": 50
    },
    {
      "epoch": 0.03218474040995313,
      "eval_loss": 0.32603439688682556,
      "eval_runtime": 633.9912,
      "eval_samples_per_second": 33.016,
      "eval_steps_per_second": 4.128,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1949222410500178e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}